SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation

Abstract

Estimating 3D orientation and translation of objects is essential for infrastructure-less autonomous navigation and driving. In case of monocular vision, successful methods have been mainly based on two ingredients: (i) a network generating 2D region proposals, (ii) a R-CNN structure predicting 3D object pose by utilizing the acquired regions of interest. We argue that the 2D detection network is redundant and introduces non-negligible noise for 3D detection. Hence, we propose a novel 3D object detection method, named SMOKE, in this paper that predicts a 3D bounding box for each detected object by combining a single keypoint estimate with regressed 3D variables. As a second contribution, we propose a multi-step disentangling approach for constructing the 3D bounding box, which significantly improves both training convergence and detection accuracy. In contrast to previous 3D detection techniques, our method does not require complicated pre/post-processing, extra data, and a refinement stage. Despite of its structural simplicity, our proposed SMOKE network outperforms all existing monocular 3D detection methods on the KITTI dataset, giving the best state-of-the-art result on both 3D object detection and Bird's eye view evaluation. The code will be made publicly available.

8 pages, 6 figures

References in corpus (14)

• Focal Loss for Dense Object Detection
• Vehicle Detection from 3D Lidar Using Fully Convolutional Network
• PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
• Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection
• Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving
• Multi-View 3D Object Detection Network for Autonomous Driving
• STD: Sparse-to-Dense 3D Object Detector for Point Cloud
• Deep Layer Aggregation
• MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization
• 3D Fully Convolutional Network for Vehicle Detection in Point Cloud
• 3D Bounding Box Estimation Using Deep Learning and Geometry
• Triangulation Learning Network: from Monocular to Stereo 3D Object Detection
• Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection
• Multi-Task Multi-Sensor Fusion for 3D Object Detection

Cited by in corpus (5)

• Geometry Uncertainty Projection Network for Monocular 3D Object Detection
• Ground-aware Monocular 3D Object Detection for Autonomous Driving
• M3DSSD: Monocular 3D Single Stage Object Detector
• Aug3D-RPN: Improving Monocular 3D Object Detection by Synthetic Images with Virtual Depth
• Exploring intermediate representation for monocular vehicle pose estimation